Metamaterials, widely studied for its counterintuitive property, are recognised to provide foundation for superior multiscale structural designs. However, current mechanical metamaterial design methods usually relay on performing sizing optimisations on predefined topology or implementing time-consuming inverse homogenisation methods. Machine Learning (ML), as a powerful self-learning tool, is considered to have the potential of discovering metamaterial topology and extending its property bounds. This work considers the use of conditional Generative Adversarial Networks (cGANs) to speed up the generation of new topologies for metamaterials. The generator in cGANs is trained to output metamaterial microstructural topologies based on the input condition, which is the desired property. Meanwhile, changing the noise input of cGANs is expected to produce different topologies, which will consequently lead to higher design diversity in metamaterial structural design. This work highlights the potential of data-driven approaches in Design for Additive Manufacturing (DfAM) as an alternative to the time-consuming, conventional methods.